CN107506845A - A kind of electricity sales amount Forecasting Methodology and its system based on multi-model fusion - Google Patents
A kind of electricity sales amount Forecasting Methodology and its system based on multi-model fusion Download PDFInfo
- Publication number
- CN107506845A CN107506845A CN201710549692.9A CN201710549692A CN107506845A CN 107506845 A CN107506845 A CN 107506845A CN 201710549692 A CN201710549692 A CN 201710549692A CN 107506845 A CN107506845 A CN 107506845A
- Authority
- CN
- China
- Prior art keywords
- forecasting methodology
- electricity
- forecasting
- prediction
- fusion
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 117
- 230000005611 electricity Effects 0.000 title claims abstract description 87
- 230000004927 fusion Effects 0.000 title claims abstract description 60
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims abstract description 5
- 238000013277 forecasting method Methods 0.000 claims description 23
- 238000007726 management method Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 4
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 238000012417 linear regression Methods 0.000 claims description 2
- 238000005267 amalgamation Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000001373 regressive effect Effects 0.000 description 1
- 230000005612 types of electricity Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention a kind of electricity sales amount Forecasting Methodology and its system based on multi-model fusion make full use of the amalgamation mode of a variety of Forecasting Methodologies, Logistics Regression Models, ARIMA forecast models and Support vector regression forecast model will be included to be organically blended to reach to the more rational prediction of electricity sales amount progress, which obviate the limitation of Individual forecast method application, the advantage of different prediction algorithms is fully used, learn from other's strong points to offset one's weaknesses, fusion forms accurate, stable electricity sales amount Forecasting Methodology.
Description
Technical field
The present invention relates to sale of electricity technical field, more particularly to a kind of electricity sales amount Forecasting Methodology based on multi-model fusion.
Background technology
With the fast development of China's power industry, the requirement more and more higher predicted in power system electricity sales amount, correctly
Predict the level of regional electricity volume sold, providing marketing decision-making for electric power enterprise supports, for instructing power plant, transmission and distribution network
Rationally operation, promote the development of electricity market and build all tools being of great significance.
Conventional Forecasting Methodology is a lot, is essentially divided into Classical forecast method and the class of intelligent predicting method two.Traditional prediction method
Mainly there are experience method, regression analysis, grey method, time series method, exponential smoothing etc..Intelligent Forecasting mainly wraps
It is pre- wavelet analysis predicted method, chaos forecast method, fuzzy theory predicted method, neural network prediction method, SVMs have been included
Survey method etc..But the application of single method has its limitation, traditional prediction method does not have to the prediction of different types of electricity sales amount
Unified and rational processing method, the less stable under the influence of weather conditions, festivals or holidays etc.；Intelligent prediction algorithms are due to influenceing
Numerous enchancement factors of electricity sales amount change are difficult to be described with mathematical modeling, and also the accuracy to prediction brings certain difficulty.
Therefore, it is necessary to design it is a kind of use a variety of mathematical method integration technologies, fully with various excellent of algorithms of different
Gesture, learn from other's strong points to offset one's weaknesses, fusion forms accurate, stable electricity sales amount forecasting system.
The content of the invention
The purpose of the present invention is the defects of presence for above-mentioned background technology, there is provided a kind of sale of electricity based on multi-model fusion
Measure Forecasting Methodology and its system.
To achieve the above object, a kind of electricity sales amount Forecasting Methodology based on multi-model fusion of one of present invention, it includes：
Step S1：The selection of Forecasting Methodology, i.e., it is pre-stored according to the prediction effect and applicable elements of Forecasting Methodology, selection
Basic skills of N number of sale of electricity Forecasting Methodology as fusion forecasting method in Forecasting Methodology storehouse；
Step S2：It is predicted using sale of electricity Forecasting Methodology, that is, utilizes each the sale of electricity prediction side selected in step S1
The set period electricity sales amount that method is predicted needs is individually predicted respectively, N number of predicted value will be obtained after prediction, i.e.,Wherein, N is the sum for calling the quantity of sale of electricity Forecasting Methodology in Forecasting Methodology storehouse, and N is nature
Number；
Step S3：The weight coefficient of each sale of electricity Forecasting Methodology in fusion forecasting method is determined, i.e., each sale of electricity Forecasting Methodology exists
Weight size w in fusion forecasting method1(t)、w2(t)……wN(t) it is individual in the preceding m of setting according to each sale of electricity Forecasting Methodology
Precision of prediction in period is determined, and the principle that weight determines is that precision is higher, and weight is bigger, wherein, m specifies for prediction
It is predicted that the period number crossed, m is natural number before period；
Step S4：N number of prediction result of calling is merged, i.e., in the t periods, by the prediction knot of each sale of electricity Forecasting Methodology
FruitAccording to weight coefficient w1(t)、w2(t)……wN(t) fusion is weighted, to be merged
The prediction result of Forecasting MethodologyPrediction resultPass through calculation formulaRealize
A kind of electricity sales amount forecasting system based on multi-model fusion of the two of the present invention, should applied to sale of electricity technical field
Forecasting system is by data acquisition and management unit, single model predicting unit, multi-model fusion forecasting unit and Forecasting Methodology storehouse group
Into；
Forecasting Methodology storehouse is made up of several fundamental forecasting method modules, and the storage one of each fundamental forecasting method module is pre-
Survey method model；
Data acquisition and management unit is used to obtaining the history electricity sales amount data in each region to be predicted, at the same also to from
Electricity sales amount prediction data, prediction error data caused by each functional unit of electricity sales amount forecasting system based on multi-model fusion study
According to and the unified management that is calculated, handled and stored such as associated parameter data, and provide information retrieval outlet and data call
Communication interface, data message is supplied to by single model predicting unit and multi-model fusion forecasting list by data call communication interface
Member；
Single model predicting unit is used for the history electricity sales amount in the region to be predicted provided according to data acquisition and management unit
Data, call multiple Individual forecast models in Forecasting Methodology storehouse to carry out tentative prediction, and arrange Storage Estimation result data；
The single model prediction data that multi-model fusion forecasting unit is used to be provided according to data acquisition and management unit calculates
The weight coefficient of each Individual forecast model in single model predicting unit, then according to the prediction result of various fundamental forecasting methods according to
Fusion is weighted according to weight coefficient, obtains the prediction result of fusion forecasting method.
In summary, the present invention a kind of Forecasting Methodology and its system based on multi-model fusion study, is avoided using single
The limitation of one Forecasting Methodology application, has fully used the advantage of different prediction algorithms, has learnt from other's strong points to offset one's weaknesses, fusion formed it is accurate,
Stable electricity sales amount Forecasting Methodology.
Brief description of the drawings
Fig. 1 is a kind of electricity sales amount Forecasting Methodology schematic flow sheet based on multi-model fusion of the present invention.
Fig. 2 is a kind of structural representation of the electricity sales amount forecasting system based on multi-model fusion of the present invention.
Embodiment
To describe technology contents, construction feature, institute's reached purpose and the effect of the present invention in detail, embodiment is hereby enumerated below
And accompanying drawing is coordinated to be explained in detail.
Referring to Fig. 1, the present invention considers the prediction result of various forecast models, with the output knot of different forecast models
Fruit is information source, and for the purpose of improving precision of prediction, maintenance data integration technology is studied electricity sales amount Forecasting Methodology.
A kind of electricity sales amount Forecasting Methodology based on multi-model fusion of one of the present invention, should applied to sale of electricity technical field
Forecasting Methodology specifically includes：
Step S1：The selection of Forecasting Methodology, i.e., it is pre-stored according to the prediction effect and applicable elements of Forecasting Methodology, selection
Basic skills of N number of sale of electricity Forecasting Methodology as fusion forecasting method in Forecasting Methodology storehouse；
Step S2：It is predicted using sale of electricity Forecasting Methodology, that is, utilizes each the sale of electricity prediction side selected in step S1
The set period electricity sales amount that method is predicted needs is individually predicted respectively, N number of predicted value will be obtained after prediction, i.e.,Wherein, N is the sum for calling the quantity of sale of electricity Forecasting Methodology in Forecasting Methodology storehouse, and N is nature
Number；
Step S3：The weight coefficient of each sale of electricity Forecasting Methodology in fusion forecasting method is determined, i.e., each sale of electricity Forecasting Methodology exists
Weight size w in fusion forecasting method1(t)、w2(t)……wN(t) it is individual in the preceding m of setting according to each sale of electricity Forecasting Methodology
Precision of prediction in period is determined, and the principle that weight determines is that precision is higher, and weight is bigger, wherein, m specifies for prediction
It is predicted that the period number crossed, m is natural number before period；
Step S4：N number of prediction result of calling is merged, i.e., in the t periods, by the prediction knot of each sale of electricity Forecasting Methodology
FruitAccording to weight coefficient w1(t)、w2(t)……wN(t) fusion is weighted, to be merged
The prediction result of Forecasting MethodologyPrediction resultPass through calculation formulaRealize.
The power to each fundamental forecasting method is needed in a kind of electricity sales amount Forecasting Methodology based on multi-model fusion of the present invention
Weight coefficient should also carry out constantly adjustment to reach the change because of season and weather temperature, and cause each fundamental forecasting method
Precision of prediction situation about constantly changing, the special weight for introducing dynamic error and calculating each fundamental forecasting method of the present invention occurs
Coefficient, solve influence of the appeal changing factor to electricity sales amount precision of prediction.
Specifically, it is e by dynamic error is definedd,i(t), and
In formula：ed,i(t) for i methods in the dynamic error of t periods, ed,i(t) it is the i sales of electricity prediction in m period before t
Method predicts error epre,i(t) average；epre,i(t) missed for the definitely relative of i sale of electricity Forecasting Methodology prediction results in the t periods
Difference.
Wherein, epre,i(t) pass throughCalculating and obtain, y (t) is the measured data of t in formula,For i methods t predicted value.
Weight coefficient wi(t) with dynamic error ed,i(t-1) the larger sale of electricity prediction of inversely proportional change, i.e. dynamic error
Method gives a less weight coefficient, and the less sale of electricity Forecasting Methodology of dynamic error gives a larger weight coefficient.
Initial weight coefficient is obtained by inverse proportion methodIn specific embodiment, weight coefficientIt is public by calculating
FormulaObtain.
Calculate final weight coefficient w of each sale of electricity Forecasting Methodology in fusion forecasting modeli(t), in specific embodiment, most
Whole weight coefficient wi(t) calculation formula is passed throughObtain.
In preferred embodiment, present invention preferably employs Logistics linear regressions, ARIMA model predictions and
Support vector regression predicts that three kinds of models carry out fusion forecasting.
A kind of forecasting system based on multi-model fusion study of the two of the present invention, applied to sale of electricity technical field, this is pre-
Examining system is made up of data acquisition and management unit, single model predicting unit, multi-model fusion forecasting unit and Forecasting Methodology storehouse.
Forecasting Methodology storehouse is made up of several fundamental forecasting method modules, and the storage one of each fundamental forecasting method module is pre-
Survey method model.Forecasting Methodology storehouse at least prestores Logistics Regression Models, ARIMA forecast models and support
Vector machine regressive prediction model.
Data acquisition and management unit is used to obtaining the history electricity sales amount data in each region to be predicted, at the same also to from
Electricity sales amount prediction data, prediction error data caused by each functional unit of electricity sales amount forecasting system based on multi-model fusion study
According to and the unified management that is calculated, handled and stored such as associated parameter data, and provide information retrieval outlet and data call
Communication interface, data message is supplied to by single model predicting unit and multi-model fusion forecasting list by data call communication interface
Member.
Single model predicting unit is used for the history electricity sales amount in the region to be predicted provided according to data acquisition and management unit
Data, call multiple Individual forecast models in Forecasting Methodology storehouse to carry out tentative prediction, and arrange Storage Estimation result data.
The single model prediction data that multi-model fusion forecasting unit is used to be provided according to data acquisition and management unit calculates
The weight coefficient of each Individual forecast model in single model predicting unit, then according to the prediction result of various fundamental forecasting methods according to
Fusion is weighted according to weight coefficient, obtains the prediction result of fusion forecasting method.
The present invention a kind of Forecasting Methodology and its system based on multi-model fusion study, are avoided using Individual forecast method
The limitation of application, the advantage of different prediction algorithms is fully used, has been learnt from other's strong points to offset one's weaknesses, fusion forms accurate, stable sale of electricity
Measure Forecasting Methodology.
Techniques discussed above scheme is only presently preferred embodiments of the present invention, it is any made on the basis of the present invention it is equivalent
Conversion or replacement are included within the protection domain of the invention.
Claims (9)
1. a kind of electricity sales amount Forecasting Methodology based on multi-model fusion, applied to sale of electricity technical field, it includes：
Step S1：The selection of Forecasting Methodology, i.e., prediction is pre-stored according to the prediction effect and applicable elements of Forecasting Methodology, selection
Basic skills of N number of sale of electricity Forecasting Methodology as fusion forecasting method in method base；
Step S2：It is predicted using sale of electricity Forecasting Methodology, that is, utilizes each the sale of electricity Forecasting Methodology pair selected in step S1
The set period electricity sales amount for needing to predict individually is predicted respectively, N number of predicted value will be obtained after prediction, i.e.,Wherein, N is the sum for calling the quantity of sale of electricity Forecasting Methodology in Forecasting Methodology storehouse, and N is nature
Number；
Step S3：The weight coefficient of each sale of electricity Forecasting Methodology in fusion forecasting method is determined, i.e., each sale of electricity Forecasting Methodology is merging
Weight size w in Forecasting Methodology1(t)、w2(t)……wN(t) it is preceding m period according to each sale of electricity Forecasting Methodology in setting
Interior precision of prediction is determined, and the principle that weight determines is precision is higher, and weight is bigger, wherein, m is prediction set period
Before it is predicted that the period number crossed, m is natural number；
Step S4：N number of prediction result of calling is merged, i.e., in the t periods, by the prediction result of each sale of electricity Forecasting MethodologyAccording to weight coefficient w1(t)、w2(t)……wN(t) fusion is weighted, it is pre- to obtain fusion
The prediction result of survey methodPrediction resultPass through calculation formulaRealize.
A kind of 2. electricity sales amount Forecasting Methodology based on multi-model fusion as claimed in claim 1, it is characterised in that：In step S1
The sale of electricity Forecasting Methodology in Forecasting Methodology storehouse have Logistics linear regressions method, ARIMA model predictions method and support
Vector machine regression prediction method.
A kind of 3. electricity sales amount Forecasting Methodology based on multi-model fusion as claimed in claim 2, it is characterised in that：In step S4
The middle definition dynamic error that introduces is ed,i(t) weight coefficient w, is utilizedi(t) with dynamic error ed,i(t-1) inversely proportional change
Method obtains initial weight coefficientThat is the larger sale of electricity Forecasting Methodology of dynamic error gives a less weight coefficient,
The less sale of electricity Forecasting Methodology of dynamic error gives a larger weight coefficient；Utilize the initial weight coefficient of acquisitionMeter
Calculate final weight coefficient w of each sale of electricity Forecasting Methodology in fusion forecasting modeli(t)。
A kind of 4. electricity sales amount Forecasting Methodology based on multi-model fusion as claimed in claim 3, it is characterised in that：Dynamic error
For ed,i(t) pass throughObtain, in formula：ed,i(t) for i methods in t
The dynamic error of period, ed,i(t) it is that i sales of electricity Forecasting Methodology predicts error e in m period before tpre,i(t) average；
epre,i(t) missed for the definitely relative of i sale of electricity Forecasting Methodology prediction results in the t periods.
A kind of 5. electricity sales amount Forecasting Methodology based on multi-model fusion as claimed in claim 4, it is characterised in that：epre,i(t)
Pass throughCalculating and obtain, y (t) is the measured data of t in formula,It is i methods in t
Predicted value.
A kind of 6. electricity sales amount Forecasting Methodology based on multi-model fusion as claimed in claim 5, it is characterised in that：Weight coefficientPass through calculation formulaObtain.
A kind of 7. electricity sales amount Forecasting Methodology based on multi-model fusion as claimed in claim 6, it is characterised in that：Final weight
Coefficient wi(t) calculation formula is passed throughObtain.
A kind of 8. electricity sales amount forecasting system based on multi-model fusion, applied to sale of electricity technical field, it is characterised in that：The prediction
System is made up of data acquisition and management unit, single model predicting unit, multi-model fusion forecasting unit and Forecasting Methodology storehouse；
Forecasting Methodology storehouse is made up of several fundamental forecasting method modules, and each fundamental forecasting method module stores a prediction side
Method model；
Data acquisition and management unit is used to obtaining the history electricity sales amount data in each region to be predicted, at the same also to from based on
Multi-model fusion study each functional unit of electricity sales amount forecasting system caused by electricity sales amount prediction data, prediction error data and
The unified management that associated parameter data etc. is calculated, handled and stored, and information retrieval outlet and data call communication are provided
Interface, data message is supplied to by single model predicting unit and multi-model fusion forecasting unit by data call communication interface；
Single model predicting unit is used for the history electricity sales amount data in the region to be predicted provided according to data acquisition and management unit,
Call multiple Individual forecast models in Forecasting Methodology storehouse to carry out tentative prediction, and arrange Storage Estimation result data；
The single model prediction data that multi-model fusion forecasting unit is used to be provided according to data acquisition and management unit calculates single mode
The weight coefficient of each Individual forecast model in type predicting unit, then according to the prediction result of various fundamental forecasting methods according to power
Weight coefficient is weighted fusion, obtains the prediction result of fusion forecasting method.
A kind of 9. electricity sales amount forecasting system based on multi-model fusion as claimed in claim 8, it is characterised in that：Forecasting Methodology
Storehouse at least prestores Logistics Regression Models, ARIMA forecast models and Support vector regression forecast model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710549692.9A CN107506845A (en) | 2017-07-07 | 2017-07-07 | A kind of electricity sales amount Forecasting Methodology and its system based on multi-model fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710549692.9A CN107506845A (en) | 2017-07-07 | 2017-07-07 | A kind of electricity sales amount Forecasting Methodology and its system based on multi-model fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107506845A true CN107506845A (en) | 2017-12-22 |
Family
ID=60679562
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710549692.9A Pending CN107506845A (en) | 2017-07-07 | 2017-07-07 | A kind of electricity sales amount Forecasting Methodology and its system based on multi-model fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107506845A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108492141A (en) * | 2018-03-28 | 2018-09-04 | 联想(北京)有限公司 | A kind of prediction technique and device of multi-model fusion |
| CN108508372A (en) * | 2018-04-24 | 2018-09-07 | 中南大学 | A kind of calculating of unmanned electricity and method for early warning and system based on environmental visual fusion |
| CN108805623A (en) * | 2018-06-11 | 2018-11-13 | 浙江工业大学 | Supply prediction method for fast-selling products |
| CN109002918A (en) * | 2018-07-16 | 2018-12-14 | 国网浙江省电力有限公司经济技术研究院 | Based on drosophila optimization algorithm-support vector machines electricity sales amount prediction technique |
| CN109214586A (en) * | 2018-09-27 | 2019-01-15 | 国网河南省电力公司濮阳供电公司 | Area power grid electricity sales amount prediction technique based on Holt-Winters model |
| CN109472648A (en) * | 2018-11-20 | 2019-03-15 | 四川长虹电器股份有限公司 | Method for Sales Forecast method and server |
| CN109509033A (en) * | 2018-12-14 | 2019-03-22 | 重庆邮电大学 | A kind of user buying behavior big data prediction technique under consumer finance scene |
| CN110110774A (en) * | 2019-04-28 | 2019-08-09 | 浙江工业大学 | A kind of Solubility Prediction method in ionic liquid of the CO2 based on multi-model fusion |
| WO2020024712A1 (en) * | 2018-08-02 | 2020-02-06 | 阿里巴巴集团控股有限公司 | Method and device for predicting number of foreign transactions |
| CN110968628A (en) * | 2019-11-18 | 2020-04-07 | 广东卓维网络有限公司 | Background management system for providing electric quantity data for mobile terminal |
-
2017
- 2017-07-07 CN CN201710549692.9A patent/CN107506845A/en active Pending
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108492141A (en) * | 2018-03-28 | 2018-09-04 | 联想(北京)有限公司 | A kind of prediction technique and device of multi-model fusion |
| CN108508372A (en) * | 2018-04-24 | 2018-09-07 | 中南大学 | A kind of calculating of unmanned electricity and method for early warning and system based on environmental visual fusion |
| CN108805623A (en) * | 2018-06-11 | 2018-11-13 | 浙江工业大学 | Supply prediction method for fast-selling products |
| CN108805623B (en) * | 2018-06-11 | 2021-08-24 | 浙江工业大学 | Supply prediction method for fast-selling products |
| CN109002918A (en) * | 2018-07-16 | 2018-12-14 | 国网浙江省电力有限公司经济技术研究院 | Based on drosophila optimization algorithm-support vector machines electricity sales amount prediction technique |
| WO2020024712A1 (en) * | 2018-08-02 | 2020-02-06 | 阿里巴巴集团控股有限公司 | Method and device for predicting number of foreign transactions |
| CN109214586A (en) * | 2018-09-27 | 2019-01-15 | 国网河南省电力公司濮阳供电公司 | Area power grid electricity sales amount prediction technique based on Holt-Winters model |
| CN109472648A (en) * | 2018-11-20 | 2019-03-15 | 四川长虹电器股份有限公司 | Method for Sales Forecast method and server |
| CN109509033A (en) * | 2018-12-14 | 2019-03-22 | 重庆邮电大学 | A kind of user buying behavior big data prediction technique under consumer finance scene |
| CN109509033B (en) * | 2018-12-14 | 2023-04-07 | 重庆邮电大学 | Big data prediction method for user purchasing behavior in consumption financial scene |
| CN110110774A (en) * | 2019-04-28 | 2019-08-09 | 浙江工业大学 | A kind of Solubility Prediction method in ionic liquid of the CO2 based on multi-model fusion |
| CN110968628A (en) * | 2019-11-18 | 2020-04-07 | 广东卓维网络有限公司 | Background management system for providing electric quantity data for mobile terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107506845A (en) | A kind of electricity sales amount Forecasting Methodology and its system based on multi-model fusion | |
| Hong et al. | Probabilistic electric load forecasting: A tutorial review | |
| Jota et al. | Building load management using cluster and statistical analyses | |
| Islam et al. | Energy demand forecasting | |
| Su et al. | A systematic data-driven Demand Side Management method for smart natural gas supply systems | |
| US10740773B2 (en) | Systems and methods of utilizing multiple forecast models in forecasting customer demands for products at retail facilities | |
| Tutun et al. | A new forecasting framework for volatile behavior in net electricity consumption: A case study in Turkey | |
| Lu et al. | Study on construction material allocation policies: A simulation optimization method | |
| Xu et al. | Strategic robust mixed model assembly line balancing based on scenario planning | |
| Sadeghieh et al. | A genetic algorithm based grey goal programming (G3) approach for parts supplier evaluation and selection | |
| CN104217258B (en) | A kind of electric load sigma-t Forecasting Methodology | |
| CN107346502A (en) | A kind of iteration product marketing forecast method based on big data | |
| Lau et al. | A demand forecast model using a combination of surrogate data analysis and optimal neural network approach | |
| Batista e Silva et al. | Estimating demand for industrial and commercial land use given economic forecasts | |
| CN109727066A (en) | A kind of big industrial electricity consumers load forecasting method based on XGBoost algorithm | |
| Alamsyah et al. | Artificial neural network for Indonesian tourism demand forecasting | |
| Mohammaditabar et al. | A supplier-selection model with classification and joint replenishment of inventory items | |
| Lam et al. | An artificial neural network and entropy model for residential property price forecasting in Hong Kong | |
| Peidro et al. | Fuzzy multi-objective optimisation for master planning in a ceramic supply chain | |
| CN106204162A (en) | New networking power consumer electricity consumption mode prediction method under a kind of internet environment | |
| Marmier et al. | Structuring and integrating human knowledge in demand forecasting: a judgemental adjustment approach | |
| CN106295877B (en) | Method for predicting electric energy consumption of smart power grid | |
| CN110751327A (en) | Long-term load combination prediction method based on multiple linear regression and gray Verhulst model | |
| Yeon et al. | Application of artificial intelligence models in water quality forecasting | |
| Sun | Analysis of production and organisational management efficiency of Chinese family intelligent manufacturing enterprises based on IoT and machine learning technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171222 |